Machine Learning is a Game-Changer for Radiation Therapy

Machine Learning is a Game-Changer for Radiation Therapy
Share this:

The rise of machine-learning technologies or rather artificial intelligence (AI) is behind some key disruptions in various industries including professional sports, telecoms, agriculture, finance and automotive.

In fact, the machine-learning algorithms can help solve issues through learning from experience and without being programmed explicitly. As such, they can already translate the spoken word from one language to another, identify plagiarized academic papers, and control autonomous vehicles.

RaySearch Laboratories are convinced that the future of artificial intelligence and machine-learning is bright.

The oncology-software company located in Stockholm is currently making considerable investments, particularly in Big-data and machine-learning. Big data is a combination of applications and technologies that promise to change radiation therapy as well as other cancer-treatment modalities including surgical intervention and chemotherapy.

“Machine learning has the potential to support and augment radiation oncology teams while freeing up their time. The power of sharing knowledge through machine-learning models will have a huge impact.

Any clinic could potentially generate the same tumor target volume and radiation treatment plan as the best clinics in the world do.

Radiation oncologists and medical physicists will all learn from each other through machine-learning models,” explains RaySearch’s head of machine learning and algorithm Fredrik Löfman.

Knowledge Transfer

With such opportunities in mind, Lofman intends to scale not only RaySearch‘s in-house potential but also its cumulative domain knowledge, particularly in machine learning.

Currently, he spearheads a committed division of machine-learning engineers situated in RaySerach’s Stockholm-based headquarters.

“Ours is a multidisciplinary programme. We have mathematicians, computer scientists, and physicists with backgrounds in different industries [such as automotive and finance] that are further along with machine-learning technologies than healthcare. Cross-fertilization with these sectors is crucial,” explained Löfman.

This outward mindset is displayed in several high-profile R&D partnerships, which RaySearch hopes would help in fast-tracking its innovation in machine-learning technologies.

In academic, RaySearch is financing joint research mainly at Stockholm-based KTH Royal Institute of Technology. Clinical partners, in this case, include Boston-based, Massachusetts General Hospital and the Princess Margaret Cancer Centre located in Toronto.

“We have a history of collaboration with The Princess Margaret and Mass Gen. So, when we started the machine-learning division it was natural for us to partner with these institutions,” said Löfman.

The collaboration with Canada’s biggest radiation-therapy facility, The Princess Margret, has been existed for over 10 years and concentrates on using machine learning in automating treatment planning, especially in the radiation-therapy clinic.

The goal of this tie-up is to produce personalized treatment plans that are customized to the unique requirements of each patient and to provide workflow efficiencies Vs. manual treatment planning.

“Machine learning is a natural fit for automating the complex treatment-planning process. It will enable us to generate highly personalized radiation treatment plans more efficiently, [thereby] allowing clinical resources or specialist technical staff to dedicate more time to patient care,” explained Purdie.

RaySerach is pushing forward with the release of complex machine-learning capabilities into the radiation-oncology clinic. Also, in December the vendor intends to launch RayStation 8B*, which is the newest release of its treatment-planning software comprising machine-learning-automated treatment planning and machine-learning-automated organ segmentation.

Source PhysicsWorld

Share this:

Leave a Reply

avatar
  Subscribe  
Notify of